Ruey-Cheng Chen

Postdoctoral Fellow
Institute of Information Science
Academia Sinica
128 Academia Rd. Sec. 2
Taipei 115, Taiwan
+886 2 2788 3799 ext 1371
rueycheng@turing.csie.ntu.edu.tw

I am a computer scientist specialized in natural language processing and information retrieval, currently working at Institute of Information Science, Academia Sinica. My recent work has focused on representation, unsupervised learning, and information-theoretic methods.

I received my doctorate in 2013 from National Taiwan University. Prior to that, I worked mostly with my advisor Jieh Hsiang at the Department of Computer Science and Information Engineering. I have also spent a year visiting University of Southern California, working with Andrew Gordon at the Institute for Creative Technologies. Before starting Ph.D., I worked full-time as a research assistant at Academia Sinica in Lee-Feng Chien's group. I received my B.S. and M.S. respectively from National Taiwan University in 2001 and 2003.

Publication

Ruey-Cheng Chen. 2013. An improved MDL-based compression algorithm for unsupervised word segmentation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL '13, pages 166-170, Sofia, Bulgaria. Association for Computational Linguistics. pdf poster

Ruey-Cheng Chen and Chia-Jung Lee. 2013. An information-theoretic account of static index pruning. In Proceedings of the 36th annual international ACM SIGIR conference on Research and development in information retrieval, SIGIR '13, pages 163-172, New York, NY, USA. ACM. pdf slides

Ruey-Cheng Chen. 2013. Information preservation and its application to natural language processing. PhD Dissertation. National Taiwan University. pdf slides

Ruey-Cheng Chen, Chia-Jung Lee, Chiung-Min Tsai, and Jieh Hsiang. 2012. Information preservation in static index pruning. In Proceedings of the 21st ACM International Conference on Information and Knowledge Management, CIKM '12, pages 2487-2490, New York, NY, USA. ACM. pdf poster

Ruey-Cheng Chen, Chiung-Min Tsai, and Jieh Hsiang. 2012. A regularized compression method to unsupervised word segmentation. In Proceedings of the Twelfth Meeting of the the Special Interest Group on Computational Morphology and Phonology, SIGMORPHON '12, pages 26-34, Montreal, Canada. Association for Computational Linguistics. pdf slides

Wei-Yen Day, Chun-Yi Chi, Ruey-Cheng Chen, and Pu-Jen Cheng. 2010. Sampling the web as training data for text classification. International Journal of Digital Library Systems (IJDLS), 1(4):24-42. publisher preprint

Ruey-Cheng Chen, Chiung-Min Tsai, and Jieh Hsiang. 2010. Relevance model revisited: With multiple document representations. In Proceedings of the 6th Asia Information Retrieval Societies Conference on Information Retrieval Technology, AIRS '10, pages 37-48, Berlin, Heidelberg. Springer-Verlag. publisher preprint slides

Ruey-Cheng Chen, Reid Swanson, and Andrew Gordon. 2010. An adaptation of topic modeling to sentences. Unpublished. preprint

Chia-Jung Lee, Yi-Chun Lin, Ruey-Cheng Chen, Pei-Sen Liu, and Pu-Jen Cheng. 2009. Query formulation by selecting good terms. In Proceedings of the 21st Conference on Computational Linguistics and Speech Processing, ROCLING '09, pages 69-84, Taichung, Taiwan. pdf

Wei-Yen Day, Chun-Yi Chi, Ruey-Cheng Chen, Pu-Jen Cheng, and Pei-Sen Liu. 2009. Web mining for unsupervised classification. In Proceedings of the 21st Conference on Computational Linguistics and Speech Processing, ROCLING '09, pages 53-68, Taichung, Taiwan. pdf

Chia-Jung Lee, Yi-Chun Lin, Ruey-Cheng Chen, and Pu-Jen Cheng. 2009. Selecting effective terms for query formulation. In Proceedings of the 5th Asia Information Retrieval Symposium on Information Retrieval Technology, AIRS '09, pages 168-180, Berlin, Heidelberg. Springer-Verlag. publisher preprint

Chia-Jung Lee, Ruey-Cheng Chen, Shao-Hang Kao, and Pu-Jen Cheng. 2009. A term dependency-based approach for query terms ranking. In Proceedings of the 18th ACM conference on Information and knowledge management, CIKM '09, pages 1267-1276, New York, NY, USA. ACM. pdf

Shuo-Peng Liao, Pu-Jen Cheng, Ruey-Cheng Chen, and Lee-Feng Chien. 2005. LiveImage: Organizing Web images by relevant concepts. In Proceedings of the Workshop on the Sciences of the Artificial, WSA '05, pages 210-220, Hualien, Taiwan. pdf

Pu-Jen Cheng, Jei-Wen Teng, Ruey-Cheng Chen, Jenq-Haur Wang, Wen-Hsiang Lu, and Lee-Feng Chien. 2004. Translating unknown queries with web corpora for cross-language information retrieval. In Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval, SIGIR '04, pages 146-153, New York, NY, USA. ACM. pdf

Pao-Ann Hsiung, Farn Wang, and Ruey-Cheng Chen. 2000. On the verification of wireless transaction protocol using SGM and RED. In Proceedings of the Seventh International Conference on Real-Time Systems and Applications, RTCSA '00, Washington, DC, USA. IEEE Computer Society. pdf

Software

I am actively developing and maintaining the following software packages:

I am slowly rolling out packages for reproducing research results. Check out my github page for recent stuff.

Fast Facts

This is my curriculum vitae.

I am father of a two-year old. Also a classic rock fan, a bassist, and a Linux user. Like beers and math. (Who wouldn't?)